Low-latency Gemini model for high-volume multimodal and agent workloads
Details
| Field | Value |
|---|---|
| id | gemini-3-5-flash-lite |
| family | gemini-flash-lite |
| modality | text+image+audio+video->text |
| context_length | 1000000 |
| max_output_tokens | 65536 |
| knowledge_cutoff | 2026-03 |
| release_date | 2026-07-09 |
| is_open_weights | no |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | yes |
| supports_attachment | yes |
| input_modalities | text, image, audio, video |
| output_modalities | text |